© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5481
    Prev
    Next
    INDEX
    Explanations

    Assessed, assumptions, assigned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theta
    0.59
    खम
    0.58
     vys
    0.58
     ಹೋ
    0.58
    underscore
    0.57
     অভিন
    0.57
    mano
    0.57
    圄
    0.55
    uvre
    0.55
     Thorn
    0.55
    POSITIVE LOGITS
     égaux
    0.71
     दक्ष
    0.68
     /=
    0.65
     cuisses
    0.65
     compensated
    0.65
    requent
    0.64
     indip
    0.64
    msız
    0.63
     indipendente
    0.62
     dhat
    0.62
    Activations Density 0.110%

    No Known Activations